T
E
L
K
O
M
NIKA
T
elec
o
mm
un
ica
t
io
n Co
m
pu
t
i
ng
E
lect
ro
nics
a
nd
Co
ntr
o
l
Vo
l.
24
,
No
.
4
,
A
u
g
u
s
t
20
26
,
p
p
.
1
287
~1
2
9
3
I
SS
N:
1
6
9
3
-
6
9
3
0
,
DOI
: 1
0
.
1
2
9
2
8
/
T
E
L
KOM
NI
K
A
.
v
24
i
4
.
27777
1287
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//telko
mn
ika
.
u
a
d
.
a
c.
i
d
XG
Bo
o
st
m
o
delin
g
f
o
r spa
rse spa
re
-
pa
rts de
m
a
nd
f
o
recas
ting
B
ria
n Q
a
edi La
k
s
o
no
P
utr
a
1
,
J
er
ry
D
w
i Trij
o
y
o
P
urno
m
o
2
1
T
e
c
h
n
o
l
o
g
y
M
a
n
a
g
e
me
n
t
P
r
o
g
r
a
m,
I
n
st
i
t
u
t
T
e
k
n
o
l
o
g
i
S
e
p
u
l
u
h
N
o
p
e
mb
e
r
(
I
T
S
)
,
S
u
r
a
b
a
y
a
,
I
n
d
o
n
e
si
a
2
D
e
p
a
r
t
me
n
t
o
f
S
t
a
t
i
s
t
i
c
s,
I
n
st
i
t
u
t
T
e
k
n
o
l
o
g
i
S
e
p
u
l
u
h
N
o
p
e
mb
e
r
(
I
TS)
,
S
u
r
a
b
a
y
a
,
I
n
d
o
n
e
si
a
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Dec
11
,
2025
R
ev
i
s
ed
A
p
r
3
,
2
0
2
6
A
cc
ep
ted
Ma
y
25
,
2026
S
p
a
re
p
a
rts
d
e
m
a
n
d
i
n
m
a
n
y
in
d
u
strial
sy
ste
m
s
is
in
h
e
re
n
tl
y
s
p
a
rse
a
n
d
in
term
it
ten
t.
In
p
ra
c
ti
c
e
,
lo
n
g
p
e
rio
d
s
o
f
z
e
ro
u
sa
g
e
a
re
c
o
m
m
o
n
,
e
v
e
n
th
o
u
g
h
i
n
v
e
n
to
ry
m
u
st
stil
l
b
e
m
a
in
tain
e
d
t
o
e
n
su
re
o
p
e
ra
ti
o
n
a
l
re
li
a
b
il
it
y
.
T
h
is
situ
a
ti
o
n
i
n
c
re
a
se
s
h
o
l
d
in
g
c
o
st
s
a
n
d
th
e
risk
o
f
o
b
so
les
c
e
n
c
e
,
w
h
il
e
a
lso
li
m
it
in
g
th
e
e
ff
e
c
ti
v
e
n
e
ss
o
f
c
o
n
v
e
n
ti
o
n
a
l
f
o
re
c
a
stin
g
tec
h
n
i
q
u
e
s.
T
h
is
stu
d
y
d
e
m
o
n
stra
tes
th
a
t
a
g
lo
b
a
l
X
G
Bo
o
st
m
o
d
e
l
train
e
d
a
c
ro
s
s
m
u
lt
ip
le
sp
a
re
-
p
a
rt
it
e
m
s
si
g
n
if
ica
n
tl
y
o
u
tp
e
rf
o
r
m
s
it
e
m
-
sp
e
c
i
f
ic
m
o
d
e
ls
u
n
d
e
r
sp
a
rse
d
e
m
a
n
d
c
o
n
d
i
ti
o
n
s.
Us
i
n
g
six
y
e
a
rs
o
f
h
isto
rica
l
sp
a
re
-
p
a
rts
u
sa
g
e
a
n
d
p
ro
c
u
re
m
e
n
t
d
a
ta
f
ro
m
th
e
e
n
e
rg
y
se
c
to
r,
th
is
stu
d
y
c
o
m
p
a
re
s
g
lo
b
a
l
a
n
d
sin
g
le
-
it
e
m
e
x
tre
m
e
g
ra
d
ien
t
b
o
o
sti
n
g
(
X
G
Bo
o
st
)
m
o
d
e
li
n
g
stra
teg
ies
.
F
o
re
c
a
st
a
c
c
u
ra
c
y
is
e
v
a
lu
a
ted
u
s
in
g
m
e
a
n
a
b
so
lu
te
e
rro
r
(
M
A
E),
ro
o
t
m
e
a
n
sq
u
a
re
d
e
rro
r
(RM
S
E),
m
e
a
n
a
b
so
lu
te p
e
rc
e
n
tag
e
e
rro
r
(M
A
P
E),
a
n
d
m
e
d
ian
a
b
so
lu
te
e
rr
o
r
(M
d
A
E),
w
h
ich
is
p
a
rti
c
u
larly
su
it
a
b
le
f
o
r
z
e
ro
-
in
f
late
d
d
e
m
a
n
d
p
a
tt
e
rn
s.
T
h
e
re
su
lt
s
c
o
n
siste
n
tl
y
sh
o
w
th
a
t
t
h
e
g
lo
b
a
l
X
G
Bo
o
st
m
o
d
e
l
a
c
h
iev
e
s
lo
we
r
e
rro
rs
a
c
ro
ss
a
ll
m
e
tri
c
s.
In
p
a
rti
c
u
lar,
t
h
e
g
lo
b
a
l
m
o
d
e
l
a
tt
a
in
s
a
m
a
r
k
e
d
l
y
lo
we
r
M
d
A
E
(0
.
0
0
0
1
8
)
,
i
n
d
ica
ti
n
g
g
re
a
te
r
ro
b
u
stn
e
ss
w
h
e
n
d
e
m
a
n
d
is i
rre
g
u
lar an
d
i
n
term
it
ten
t.
K
ey
w
o
r
d
s
:
Fo
r
ec
asti
n
g
Glo
b
al
m
o
d
eli
n
g
Ma
ch
i
n
e
lear
n
i
n
g
Sin
g
le
-
ite
m
m
o
d
eli
n
g
XGB
o
o
s
t
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
B
r
ian
Qae
d
i L
ak
s
o
n
o
P
u
tr
a
T
ec
h
n
o
lo
g
y
Ma
n
ag
e
m
e
n
t P
r
o
g
r
a
m
,
I
n
s
tit
u
t T
ek
n
o
lo
g
i
Sep
u
l
u
h
No
p
e
m
b
er
(
I
T
S)
Su
r
ab
a
y
a,
I
n
d
o
n
e
s
ia
E
m
ail: b
r
ian
.
q
ae
d
i@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
Sp
ar
e
-
p
ar
ts
d
em
a
n
d
in
m
a
n
y
in
d
u
s
tr
ial
s
etti
n
g
s
is
ch
ar
ac
te
r
ized
b
y
s
p
ar
s
e
an
d
in
ter
m
itt
en
t
u
s
a
g
e,
w
h
er
e
lo
n
g
p
er
io
d
s
o
f
ze
r
o
d
em
a
n
d
ar
e
co
m
m
o
n
w
h
i
le
in
v
e
n
to
r
y
m
u
s
t
s
t
ill
b
e
m
a
in
tai
n
ed
to
en
s
u
r
e
o
p
er
atio
n
al
co
n
tin
u
it
y
[
1
]
–
[
3
]
.
T
h
is
co
n
d
itio
n
in
cr
ea
s
es
in
v
e
n
to
r
y
h
o
ld
in
g
co
s
ts
a
n
d
th
e
r
is
k
o
f
o
b
s
o
lescen
c
e,
p
ar
ticu
lar
l
y
f
o
r
s
lo
w
-
m
o
v
i
n
g
an
d
cr
itical
co
m
p
o
n
e
n
t
s
[
4
]
,
[
5
]
.
C
o
n
v
en
tio
n
al
f
o
r
ec
asti
n
g
ap
p
r
o
ac
h
es,
in
cl
u
d
in
g
class
ica
l
ti
m
e
-
s
er
ie
s
an
d
in
ter
m
i
tt
en
t
-
d
e
m
an
d
m
et
h
o
d
s
,
o
f
ten
s
tr
u
g
g
le
u
n
d
er
s
u
ch
co
n
d
itio
n
s
,
esp
ec
iall
y
w
h
e
n
h
i
s
to
r
ical
o
b
s
er
v
atio
n
s
ar
e
li
m
ited
[
3
]
,
[
5
]
.
I
n
th
e
d
ataset
a
n
al
y
ze
d
in
t
h
is
s
tu
d
y
(
2
0
2
0
–
2
0
2
5
)
,
ap
p
r
o
x
im
a
tel
y
9
0
.
6
%
o
f
m
o
n
th
l
y
o
b
s
er
v
atio
n
s
co
r
r
esp
o
n
d
to
ze
r
o
d
em
an
d
,
co
n
f
ir
m
i
n
g
th
e
h
ig
h
l
y
s
p
ar
s
e
n
atu
r
e
o
f
s
p
ar
e
-
p
ar
ts
u
s
a
g
e.
T
o
ad
d
r
ess
th
ese
ch
a
llen
g
es,
m
ac
h
in
e
-
lear
n
i
n
g
-
b
ased
f
o
r
ec
as
tin
g
m
et
h
o
d
s
h
a
v
e
b
ee
n
in
cr
ea
s
in
g
l
y
ad
o
p
ted
d
u
e
to
th
eir
ab
ilit
y
to
m
o
d
el
n
o
n
-
lin
ea
r
r
elatio
n
s
h
ip
s
a
n
d
h
a
n
d
le
h
eter
o
g
en
eo
u
s
d
ata
s
tr
u
ct
u
r
es
[
6
]
.
Am
o
n
g
t
h
ese
m
et
h
o
d
s
,
tr
e
e
-
b
ased
e
n
s
e
m
b
le
al
g
o
r
ith
m
s
,
p
ar
ticu
lar
ly
ex
tr
e
m
e
g
r
ad
ien
t
b
o
o
s
tin
g
(
XGB
o
o
s
t)
,
h
a
v
e
d
e
m
o
n
s
tr
ated
s
tr
o
n
g
p
er
f
o
r
m
a
n
ce
i
n
f
o
r
ec
asti
n
g
ta
s
k
s
i
n
v
o
lv
i
n
g
ir
r
eg
u
lar
an
d
ze
r
o
-
in
f
lated
d
e
m
a
n
d
[
7
]
–
[
9
]
.
B
ey
o
n
d
alg
o
r
ith
m
s
elec
tio
n
,
t
h
e
m
o
d
elin
g
s
tr
ateg
y
its
el
f
p
la
y
s
a
cr
itical
r
o
le
w
h
en
d
e
m
a
n
d
d
ata
ar
e
s
p
ar
s
e.
Glo
b
al
m
o
d
elin
g
ap
p
r
o
ac
h
es
tr
ain
a
s
in
g
le
m
o
d
el
ac
r
o
s
s
m
u
lt
ip
le
ite
m
s
,
en
ab
l
in
g
s
h
ar
ed
d
e
m
an
d
p
atter
n
s
to
b
e
lear
n
ed
jo
in
tl
y
,
w
h
er
ea
s
s
in
g
le
-
ite
m
m
o
d
els
ar
e
tr
ain
ed
in
d
ep
en
d
en
tl
y
f
o
r
ea
ch
ite
m
[
1
]
,
[
2
]
.
P
r
io
r
s
tu
d
ies
r
ep
o
r
t
th
at
g
lo
b
al
m
o
d
els
o
f
te
n
p
r
o
v
id
e
m
o
r
e
r
o
b
u
s
t
f
o
r
ec
asts
w
h
e
n
in
d
i
v
id
u
al
ti
m
e
s
er
ies
ar
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
24
,
No
.
4
,
A
u
g
u
s
t
20
26
:
1
287
-
1
2
9
3
1288
s
h
o
r
t
o
r
h
i
g
h
l
y
i
n
ter
m
itte
n
t
[
1
0
]
.
Ho
w
ev
er
,
e
m
p
ir
ical
co
m
p
ar
is
o
n
s
b
et
w
ee
n
g
lo
b
al
an
d
ite
m
-
s
p
ec
if
ic
XGB
o
o
s
t
m
o
d
els
f
o
r
h
i
g
h
l
y
s
p
ar
s
e
s
p
ar
e
-
p
ar
ts
d
e
m
a
n
d
r
em
ai
n
li
m
ited
,
p
ar
ticu
lar
l
y
in
in
d
u
s
tr
ial
i
n
v
en
to
r
y
co
n
tex
t
s
.
T
ab
le
1
s
u
m
m
ar
ize
s
r
ep
r
esen
tat
iv
e
s
t
u
d
ies co
m
p
ar
i
n
g
g
lo
b
al
an
d
s
i
n
g
le
-
ite
m
f
o
r
e
ca
s
tin
g
ap
p
r
o
ac
h
es
ac
r
o
s
s
d
if
f
er
en
t
ap
p
licatio
n
d
o
m
a
in
s
.
T
h
is
o
v
er
v
ie
w
m
o
t
iv
ates
t
h
e
f
o
cu
s
o
f
th
e
p
r
esen
t
s
tu
d
y
o
n
co
m
p
ar
in
g
g
lo
b
al
an
d
s
i
n
g
le
-
ite
m
XGB
o
o
s
t
m
o
d
els f
o
r
s
p
ar
s
e
s
p
ar
e
-
p
a
r
ts
d
e
m
an
d
f
o
r
ec
asti
n
g
.
T
ab
le
1
.
C
o
m
p
ar
is
o
n
o
f
g
lo
b
al
an
d
s
in
g
le
-
ite
m
f
o
r
ec
asti
n
g
a
p
p
r
o
ac
h
es in
p
r
ev
io
u
s
s
tu
d
ie
s
R
e
f
.
F
o
c
u
s
D
a
t
a
se
t
/
a
p
p
l
i
c
a
t
i
o
n
d
o
mai
n
M
e
t
h
o
d
s /
a
l
g
o
r
i
t
h
ms
K
e
y
c
o
n
t
r
i
b
u
t
i
o
n
[
1
]
G
l
o
b
a
l
mo
d
e
l
i
n
g
f
o
r
g
r
o
u
p
e
d
t
i
me
se
r
i
e
s
L
a
r
g
e
-
sca
l
e
f
o
r
e
c
a
st
i
n
g
c
o
mp
e
t
i
t
i
o
n
d
a
t
a
se
t
s
G
l
o
b
a
l
r
e
c
u
r
r
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
s
(
R
N
N
)
D
e
mo
n
st
r
a
t
e
d
t
h
a
t
g
l
o
b
a
l
mo
d
e
l
s o
u
t
p
e
r
f
o
r
m
l
o
c
a
l
mo
d
e
l
s b
y
sh
a
r
i
n
g
i
n
f
o
r
ma
t
i
o
n
a
c
r
o
ss
r
e
l
a
t
e
d
t
i
me
se
r
i
e
s,
p
a
r
t
i
c
u
l
a
r
l
y
w
h
e
n
i
n
d
i
v
i
d
u
a
l
se
r
i
e
s a
r
e
sh
o
r
t
o
r
s
p
a
r
se
[
2
]
G
l
o
b
a
l
mo
d
e
l
i
n
g
u
n
d
e
r
h
e
t
e
r
o
g
e
n
e
o
u
s
d
e
man
d
p
a
t
t
e
r
n
s
D
i
v
e
r
se
r
e
a
l
-
w
o
r
l
d
f
o
r
e
c
a
st
i
n
g
d
a
t
a
se
t
s
G
l
o
b
a
l
p
r
o
b
a
b
i
l
i
s
t
i
c
f
o
r
e
c
a
st
i
n
g
mo
d
e
l
s
R
e
p
o
r
t
e
d
t
h
a
t
g
l
o
b
a
l
mo
d
e
l
s a
c
h
i
e
v
e
mo
r
e
r
o
b
u
st
p
e
r
f
o
r
man
c
e
a
c
r
o
ss se
r
i
e
s w
i
t
h
v
a
r
y
i
n
g
d
e
man
d
c
h
a
r
a
c
t
e
r
i
st
i
c
s
[
5
]
S
i
n
g
l
e
-
i
t
e
m (l
o
c
a
l
)
mo
d
e
l
i
n
g
f
o
r
i
n
t
e
r
mi
t
t
e
n
t
d
e
ma
n
d
S
p
a
r
e
p
a
r
t
s
a
n
d
i
n
t
e
r
mi
t
t
e
n
t
d
e
man
d
d
a
t
a
se
t
s
C
r
o
st
o
n
-
b
a
se
d
l
o
c
a
l
f
o
r
e
c
a
st
i
n
g
me
t
h
o
d
s
I
d
e
n
t
i
f
i
e
d
p
e
r
f
o
r
man
c
e
l
i
mi
t
a
t
i
o
n
s
o
f
si
n
g
l
e
-
i
t
e
m mo
d
e
l
s w
h
e
n
h
i
st
o
r
i
c
a
l
d
e
ma
n
d
o
b
se
r
v
a
t
i
o
n
s
a
r
e
sp
a
r
se
a
n
d
h
i
g
h
l
y
i
n
t
e
r
mi
t
t
e
n
t
[
9
]
G
l
o
b
a
l
mo
d
e
l
i
n
g
f
o
r
e
n
e
r
g
y
d
e
man
d
f
o
r
e
c
a
st
i
n
g
En
e
r
g
y
c
o
n
su
mp
t
i
o
n
a
n
d
smar
t
-
me
t
e
r
d
a
t
a
G
l
o
b
a
l
l
o
n
g
sh
o
r
t
-
t
e
r
m
me
mo
r
y
(
L
S
T
M
)
–
X
G
B
o
o
st
h
y
b
r
i
d
mo
d
e
l
s
R
e
p
o
r
t
e
d
t
h
a
t
g
l
o
b
a
l
l
e
a
r
n
i
n
g
a
c
r
o
ss
mu
l
t
i
p
l
e
se
r
i
e
s i
mp
r
o
v
e
s ro
b
u
st
n
e
ss a
n
d
p
r
e
d
i
c
t
i
o
n
a
c
c
u
r
a
c
y
u
n
d
e
r
n
o
n
-
l
i
n
e
a
r
a
n
d
f
l
u
c
t
u
a
t
i
n
g
d
e
man
d
p
a
t
t
e
r
n
s
[
1
0
]
G
l
o
b
a
l
mo
d
e
l
i
n
g
f
o
r
mu
l
t
i
p
l
e
t
i
me
se
r
i
e
s
R
e
t
a
i
l
a
n
d
d
e
man
d
t
i
me
-
se
r
i
e
s d
a
t
a
G
l
o
b
a
l
mac
h
i
n
e
l
e
a
r
n
i
n
g
–
b
a
se
d
f
o
r
e
c
a
st
i
n
g
mo
d
e
l
s
R
e
p
o
r
t
e
d
i
mp
r
o
v
e
d
f
o
r
e
c
a
st
a
c
c
u
r
a
c
y
a
n
d
st
a
b
i
l
i
t
y
c
o
mp
a
r
e
d
t
o
si
n
g
l
e
-
i
t
e
m mo
d
e
l
s
u
n
d
e
r
d
a
t
a
sc
a
r
c
i
t
y
2.
M
E
T
H
O
D
2
.
1
.
Resea
rc
h
w
o
r
k
f
lo
w
T
h
is
s
t
u
d
y
ad
o
p
ts
a
q
u
an
t
itat
iv
e
r
esear
c
h
d
esi
g
n
to
ev
a
lu
a
te
t
w
o
f
o
r
ec
ast
in
g
s
tr
ateg
ie
s
f
o
r
s
p
ar
s
e
s
p
ar
e
-
p
ar
ts
d
e
m
a
n
d
b
ased
o
n
a
m
ac
h
i
n
e
-
lear
n
i
n
g
m
o
d
el.
Sp
ec
if
icall
y
,
t
h
e
s
tr
ateg
ies
c
o
m
p
ar
e
g
lo
b
al
an
d
s
in
g
le
-
ite
m
m
o
d
elin
g
ap
p
r
o
ac
h
es
u
s
in
g
XGB
o
o
s
t.
T
h
e
w
o
r
k
f
lo
w
co
n
s
i
s
ts
o
f
d
ata
co
llectio
n
a
n
d
p
r
ep
r
o
ce
s
s
in
g
,
f
ea
t
u
r
e
en
g
i
n
ee
r
in
g
,
m
o
d
el
d
ev
e
lo
p
m
en
t,
ti
m
e
-
b
ased
d
ata
s
p
litt
i
n
g
,
a
n
d
m
o
d
el
ev
alu
atio
n
.
2
.
2
.
Da
t
a
s
et
a
nd
f
ea
t
ure
eng
ineering
T
h
e
an
al
y
s
i
s
u
s
es
m
o
n
t
h
l
y
s
p
ar
e
-
p
ar
ts
u
s
a
g
e
an
d
p
r
o
cu
r
em
en
t
r
ec
o
r
d
s
o
b
tain
ed
f
r
o
m
an
en
er
g
y
-
s
ec
to
r
o
r
g
an
izatio
n
o
v
er
a
s
i
x
-
y
ea
r
p
er
io
d
(
2
0
2
0
–
2
0
2
5
)
.
A
p
u
r
p
o
s
iv
e
s
a
m
p
li
n
g
ap
p
r
o
ac
h
w
as
ad
o
p
ted
to
co
n
ce
n
tr
ate
o
n
s
p
ar
e
p
ar
ts
t
h
at
e
x
h
ib
it
s
p
ar
s
e
a
n
d
in
ter
m
itte
n
t
d
e
m
an
d
,
w
h
ic
h
i
s
t
y
p
ica
l
i
n
i
n
d
u
s
tr
ial
m
ai
n
ten
a
n
ce
e
n
v
ir
o
n
m
en
t
s
.
Featu
r
e
e
n
g
in
ee
r
i
n
g
w
as
ap
p
lied
to
co
n
v
er
t
r
a
w
tr
a
n
s
a
ctio
n
al
r
ec
o
r
d
s
in
to
m
ea
n
in
g
f
u
l
i
n
p
u
t
v
ar
iab
les
f
o
r
m
ac
h
i
n
e
-
lear
n
i
n
g
m
o
d
eli
n
g
u
n
d
er
s
p
ar
s
e
d
e
m
an
d
co
n
d
itio
n
s
.
T
e
m
p
o
r
al
f
ea
t
u
r
es
w
er
e
d
er
iv
ed
f
r
o
m
h
is
to
r
ical
u
s
a
g
e
an
d
p
r
o
cu
r
e
m
en
t
d
ata
to
ca
p
tu
r
e
r
ec
en
t
d
e
m
an
d
b
eh
a
v
io
r
.
I
n
p
ar
ticu
lar
,
t
w
o
-
m
o
n
t
h
la
g
v
ar
i
ab
les
w
er
e
i
n
cl
u
d
ed
to
r
ep
r
es
en
t
s
h
o
r
t
-
ter
m
d
ep
en
d
en
c
y
,
r
ef
lecti
n
g
th
e
l
i
m
ited
m
e
m
o
r
y
co
m
m
o
n
l
y
o
b
s
er
v
ed
in
in
ter
m
itten
t
d
e
m
an
d
.
R
o
ll
in
g
f
ea
t
u
r
es
w
er
e
ca
lcu
lated
to
s
m
o
o
t
h
ir
r
eg
u
lar
m
o
n
t
h
-
to
-
m
o
n
th
f
lu
c
tu
at
io
n
s
an
d
p
r
o
v
id
e
a
m
o
r
e
s
tab
le
r
ep
r
esen
tatio
n
o
f
r
ec
en
t
d
e
m
a
n
d
lev
els.
T
o
p
r
eser
v
e
th
e
te
m
p
o
r
al
o
r
d
er
o
f
o
b
s
er
v
atio
n
s
,
ad
d
itio
n
al
ti
m
e
-
r
elate
d
i
n
d
icato
r
s
s
u
c
h
as
m
o
n
th
an
d
y
ea
r
w
er
e
in
cl
u
d
ed
.
T
h
ese
in
d
icato
r
s
h
elp
th
e
m
o
d
el
d
is
tin
g
u
is
h
b
et
w
ee
n
d
if
f
er
en
t
p
er
io
d
s
in
th
e
h
is
to
r
ical
d
ata
w
h
ile
av
o
id
in
g
th
e
i
m
p
o
s
itio
n
o
f
s
tr
o
n
g
o
r
p
r
ed
ef
in
ed
s
ea
s
o
n
al
p
atter
n
s
.
T
h
e
f
in
al
s
et
o
f
en
g
i
n
ee
r
ed
f
ea
t
u
r
es
r
es
u
lti
n
g
f
r
o
m
th
is
p
r
o
ce
s
s
i
s
s
u
m
m
ar
ized
an
d
d
is
cu
s
s
ed
i
n
th
e
r
es
u
lt
s
s
ec
ti
o
n
.
2
.
3
.
M
o
delin
g
s
t
ra
t
eg
y
a
nd
hy
perpa
ra
m
et
er
co
nfig
ura
t
i
o
n
Fo
r
ec
asti
n
g
m
o
d
els
w
er
e
d
ev
elo
p
ed
u
s
in
g
XGB
o
o
s
t,
a
tr
ee
-
b
ased
en
s
e
m
b
le
lear
n
in
g
al
g
o
r
ith
m
t
h
at
in
cr
e
m
e
n
tall
y
i
m
p
r
o
v
e
s
p
r
ed
ictiv
e
p
er
f
o
r
m
an
ce
th
r
o
u
g
h
g
r
ad
ien
t
b
o
o
s
tin
g
o
p
ti
m
izatio
n
[
7
]
.
T
w
o
m
o
d
eli
n
g
s
tr
ateg
ie
s
w
er
e
ex
a
m
i
n
ed
.
I
n
t
h
e
g
lo
b
al
m
o
d
eli
n
g
ap
p
r
o
ac
h
,
a
s
in
g
le
XGB
o
o
s
t
m
o
d
el
w
a
s
tr
ain
ed
o
n
p
o
o
led
o
b
s
er
v
atio
n
s
f
r
o
m
m
u
l
tip
le
s
p
ar
e
-
p
ar
ts
ite
m
s
,
allo
w
i
n
g
th
e
m
o
d
el
to
lear
n
s
h
ar
ed
d
e
m
a
n
d
s
tr
u
ct
u
r
es
ac
r
o
s
s
ite
m
s
.
I
n
co
n
tr
as
t,
th
e
s
in
g
le
-
ite
m
m
o
d
elin
g
ap
p
r
o
ac
h
tr
ain
ed
in
d
ep
en
d
en
t
XGB
o
o
s
t
m
o
d
els
f
o
r
ea
ch
s
p
ar
e
p
ar
t u
s
in
g
ite
m
-
s
p
ec
i
f
ic
h
is
to
r
i
ca
l d
ata,
w
h
ic
h
ca
n
li
m
it
m
o
d
e
l stab
ilit
y
w
h
e
n
o
b
s
er
v
atio
n
s
a
r
e
s
p
ar
s
e
[
2
]
,
[
5
]
.
T
r
a
d
itio
n
al
f
o
r
ec
asti
n
g
ap
p
r
o
ac
h
es
co
m
m
o
n
l
y
u
s
ed
f
o
r
i
n
ter
m
itte
n
t
d
e
m
a
n
d
,
s
u
c
h
a
s
a
u
to
r
eg
r
ess
i
v
e
in
te
g
r
ate
d
m
o
v
i
n
g
av
er
ag
e
(
AR
I
M
A
)
-
b
ased
m
o
d
els
a
n
d
C
r
o
s
to
n
-
t
y
p
e
m
eth
o
d
s
,
ar
e
p
r
i
m
ar
il
y
d
es
ig
n
ed
f
o
r
ite
m
-
le
v
el
an
al
y
s
is
.
W
h
ile
t
h
ese
m
et
h
o
d
s
ar
e
ef
f
ec
ti
v
e
f
o
r
in
d
iv
id
u
al
ti
m
e
s
er
ies
w
it
h
s
u
f
f
icie
n
t
h
i
s
to
r
ical
d
ata,
th
e
y
h
a
v
e
li
m
ited
ca
p
ab
ilit
y
to
ca
p
tu
r
e
s
h
ar
ed
p
at
ter
n
s
ac
r
o
s
s
m
u
ltip
le
h
eter
o
g
e
n
eo
u
s
ite
m
s
.
A
s
a
r
es
u
lt,
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
X
GB
o
o
s
t m
o
d
elin
g
fo
r
s
p
a
r
s
e
s
p
a
r
e
-
p
a
r
ts
d
ema
n
d
fo
r
ec
a
s
tin
g
(
B
r
ia
n
Qa
ed
i La
kso
n
o
P
u
tr
a
)
1289
th
eir
p
er
f
o
r
m
an
ce
o
f
te
n
d
eg
r
ad
es
w
h
e
n
d
e
m
a
n
d
d
ata
ar
e
s
p
ar
s
e
an
d
h
ig
h
l
y
i
n
ter
m
i
tten
t.
T
h
er
ef
o
r
e,
C
r
o
s
to
n
-
t
y
p
e
an
d
AR
I
M
A
-
b
ased
m
et
h
o
d
s
ar
e
n
o
t
in
clu
d
ed
as
n
u
m
er
ical
b
aseli
n
es
i
n
th
i
s
s
t
u
d
y
,
as
t
h
e
p
r
i
m
ar
y
o
b
j
ec
tiv
e
is
to
is
o
late
th
e
ef
f
e
ct
o
f
g
lo
b
al
v
er
s
u
s
s
in
g
le
-
ite
m
m
o
d
eli
n
g
s
tr
ateg
ie
s
w
ith
in
a
co
n
s
is
ten
t
m
ac
h
in
e
-
lear
n
in
g
f
r
a
m
e
w
o
r
k
r
at
h
er
th
a
n
to
co
m
p
ar
e
d
if
f
er
e
n
t c
las
s
es
o
f
f
o
r
ec
asti
n
g
al
g
o
r
it
h
m
s
[
3
]
,
[
5
]
.
I
n
th
e
g
lo
b
al
m
o
d
elin
g
ap
p
r
o
ac
h
,
in
d
i
v
id
u
al
s
p
ar
e
-
p
ar
t
item
s
ar
e
d
is
ti
n
g
u
i
s
h
ed
i
m
p
l
icit
l
y
th
r
o
u
g
h
th
eir
h
i
s
to
r
ical
u
s
a
g
e
an
d
p
r
o
cu
r
e
m
e
n
t
p
atter
n
s
r
at
h
er
th
an
th
r
o
u
g
h
ex
p
licit
ca
te
g
o
r
ical
en
co
d
in
g
.
I
te
m
id
en
ti
f
ier
s
ar
e
r
etain
ed
o
n
ly
to
as
s
o
ciate
o
b
s
er
v
atio
n
s
w
it
h
th
e
s
a
m
e
ite
m
,
w
h
i
le
s
h
ar
ed
d
em
a
n
d
ch
ar
ac
ter
is
tic
s
ar
e
lear
n
ed
f
r
o
m
n
u
m
er
ica
l
f
ea
t
u
r
es
s
u
c
h
as
lag
g
ed
u
s
ag
e,
r
o
llin
g
ag
g
r
eg
a
tes,
an
d
in
v
e
n
to
r
y
-
r
elate
d
v
ar
iab
les.
T
h
is
d
esig
n
allo
w
s
th
e
XGB
o
o
s
t
m
o
d
el
to
g
en
er
alize
ac
r
o
s
s
m
u
lt
ip
le
item
s
w
ith
o
u
t
r
eq
u
ir
in
g
e
x
p
licit ite
m
-
le
v
el
e
n
co
d
in
g
.
Z
er
o
-
d
e
m
an
d
o
b
s
er
v
atio
n
s
ar
e
f
u
l
l
y
r
etai
n
ed
d
u
r
in
g
b
o
th
tr
ain
i
n
g
a
n
d
ev
al
u
atio
n
to
r
ef
le
ct
th
e
tr
u
e
in
ter
m
itte
n
t
n
at
u
r
e
o
f
s
p
ar
e
-
p
ar
ts
d
em
a
n
d
.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
s
g
e
n
er
ate
p
o
in
t
f
o
r
ec
asts
o
f
ex
ac
t
d
e
m
a
n
d
q
u
an
tit
ies
r
ath
er
t
h
a
n
p
r
o
b
ab
il
it
y
-
w
ei
g
h
ted
o
u
tp
u
ts
.
R
o
b
u
s
t
n
ess
to
ze
r
o
-
in
f
lated
d
e
m
a
n
d
is
th
er
ef
o
r
e
ass
e
s
s
ed
th
r
o
u
g
h
er
r
o
r
-
b
ased
ev
a
lu
at
io
n
m
etr
ics,
p
ar
ticu
lar
l
y
t
h
e
m
ed
ian
ab
s
o
lu
te
er
r
o
r
(
Md
A
E
)
,
w
h
ic
h
p
r
o
v
id
es
a
s
tab
le
r
ep
r
esen
tatio
n
o
f
t
y
p
ica
l f
o
r
ec
asti
n
g
er
r
o
r
u
n
d
er
s
p
ar
s
e
d
em
a
n
d
co
n
d
itio
n
s
.
R
ec
en
t
d
ev
elo
p
m
en
t
s
in
m
a
ch
in
e
-
lear
n
i
n
g
-
b
ased
ti
m
e
-
s
er
ies
f
o
r
ec
asti
n
g
s
u
g
g
e
s
t
th
at
co
m
p
le
x
te
m
p
o
r
al
d
y
n
a
m
ics
ca
n
b
e
m
o
d
eled
m
o
r
e
ef
f
ec
ti
v
el
y
w
h
e
n
i
n
f
o
r
m
atio
n
i
s
lear
n
ed
j
o
in
tl
y
a
cr
o
s
s
r
elate
d
s
er
ies
[
1
1
]
,
[
1
2
]
.
Neu
r
al
f
o
r
ec
asti
n
g
ap
p
r
o
ac
h
es
f
u
r
t
h
er
s
u
p
p
o
r
t
th
is
ca
p
ab
ilit
y
b
y
ca
p
t
u
r
in
g
n
o
n
-
lin
ea
r
d
e
m
a
n
d
b
eh
av
io
r
in
s
p
ar
s
e
an
d
h
i
g
h
-
d
i
m
en
s
io
n
a
l
s
etti
n
g
s
[
1
3
]
,
[
1
4
]
.
P
r
o
b
ab
ilis
tic
f
o
r
ec
asti
n
g
m
o
d
els
ex
te
n
d
th
is
id
ea
b
y
ex
p
lic
itl
y
m
o
d
eli
n
g
u
n
ce
r
tain
t
y
a
n
d
v
ar
iab
ilit
y
i
n
in
ter
m
itte
n
t
d
e
m
a
n
d
p
atter
n
s
[
1
5
]
,
[
1
6
]
.
I
n
ad
d
itio
n
,
lar
g
e
-
s
ca
le
g
lo
b
al
lear
n
i
n
g
f
r
a
m
e
w
o
r
k
s
h
a
v
e
b
ee
n
s
h
o
w
n
to
i
m
p
r
o
v
e
f
o
r
ec
ast
in
g
r
o
b
u
s
t
n
e
s
s
i
n
in
d
u
s
tr
ial
a
n
d
en
er
g
y
-
r
ela
ted
ap
p
licatio
n
s
,
p
ar
ticu
lar
l
y
w
h
e
n
in
d
i
v
id
u
al
t
i
m
e
s
er
ies
ar
e
s
h
o
r
t
o
r
h
ig
h
l
y
in
ter
m
i
tten
t
[
1
7
]
,
[
1
8
]
.
Sim
ilar
b
en
e
f
i
ts
o
f
cr
o
s
s
-
s
er
ies lea
r
n
i
n
g
h
av
e
al
s
o
b
ee
n
r
ep
o
r
ted
in
r
ec
en
t s
tu
d
ie
s
f
o
c
u
s
in
g
o
n
n
e
u
r
al
an
d
s
tate
-
s
p
ac
e
-
b
ased
f
o
r
ec
ast
in
g
m
o
d
els
[
1
9
]
–
[
2
1
]
,
as
w
ell
as
in
b
r
o
ad
er
s
u
r
v
e
y
s
o
f
lar
g
e
-
s
ca
le
ti
m
e
-
s
er
ies
f
o
r
ec
asti
n
g
m
e
th
o
d
s
[
2
2
]
–
[
2
5
]
.
A
g
ai
n
s
t
th
is
m
et
h
o
d
o
lo
g
ica
l
b
ac
k
g
r
o
u
n
d
,
th
e
p
r
esen
t
s
t
u
d
y
ad
o
p
ts
XGB
o
o
s
t
as
a
r
ep
r
esen
tati
v
e
m
ac
h
in
e
-
lear
n
in
g
m
o
d
el
an
d
f
o
cu
s
e
s
o
n
co
m
p
ar
in
g
g
lo
b
al
an
d
s
i
n
g
le
-
ite
m
m
o
d
eli
n
g
s
tr
ateg
ie
s
.
T
h
e
co
n
ce
p
tu
al
d
i
f
f
er
en
ce
b
et
w
ee
n
g
lo
b
al
an
d
s
in
g
le
-
ite
m
m
o
d
eli
n
g
s
tr
ateg
ies
ad
o
p
ted
in
th
i
s
s
tu
d
y
is
ill
u
s
tr
ated
in
Fi
g
u
r
e
1
.
Fo
r
th
e
g
lo
b
al
XGB
o
o
s
t
m
o
d
el,
k
e
y
h
y
p
er
p
ar
a
m
eter
s
w
er
e
s
elec
ted
th
r
o
u
g
h
p
r
eli
m
i
n
ar
y
tu
n
in
g
to
b
alan
ce
m
o
d
el
co
m
p
lex
it
y
an
d
g
en
er
aliza
tio
n
u
n
d
er
s
p
ar
s
e
d
em
a
n
d
co
n
d
itio
n
s
.
T
h
e
lear
n
in
g
r
ate
w
as
s
e
t
to
0
.
0
5
,
th
e
m
a
x
i
m
u
m
tr
ee
d
ep
th
w
as
li
m
ited
to
4
,
an
d
th
e
n
u
m
b
er
o
f
b
o
o
s
ti
n
g
tr
ee
s
w
a
s
f
i
x
ed
at
3
0
0
.
I
n
ad
d
itio
n
,
s
u
b
s
a
m
p
le
an
d
co
ls
a
m
p
le_
b
y
tr
ee
r
atio
s
w
er
e
s
et
to
0
.
8
to
im
p
r
o
v
e
r
o
b
u
s
tn
e
s
s
a
n
d
r
ed
u
ce
th
e
r
is
k
o
f
o
v
er
f
itti
n
g
.
Fig
u
r
e
1
.
C
o
m
p
ar
is
o
n
o
f
g
lo
b
al
an
d
s
in
g
le
-
ite
m
m
o
d
eli
n
g
s
t
r
ateg
ies
f
o
r
s
p
ar
s
e
s
p
ar
e
p
ar
ts
d
em
a
n
d
2
.
4
.
M
o
del
ev
a
lua
t
i
o
n
A
ti
m
e
-
b
ased
d
ata
-
s
p
litt
in
g
s
tr
ateg
y
w
as
e
m
p
lo
y
ed
to
p
r
eser
v
e
te
m
p
o
r
al
s
tr
u
ct
u
r
e
an
d
p
r
ev
en
t
in
f
o
r
m
atio
n
lea
k
ag
e.
Data
f
r
o
m
2
0
2
0
to
2
0
2
4
w
er
e
u
s
ed
f
o
r
tr
ain
in
g
,
w
h
ile
2
0
2
5
d
at
a
w
er
e
r
eser
v
ed
f
o
r
test
i
n
g
.
Fo
r
ec
ast
ac
cu
r
ac
y
w
as
ass
ess
ed
u
s
i
n
g
m
ea
n
ab
s
o
lu
te
er
r
o
r
(
MA
E
)
,
r
o
o
t
m
ea
n
s
q
u
a
r
ed
er
r
o
r
(
R
MSE
)
,
m
ea
n
ab
s
o
l
u
te
p
er
ce
n
ta
g
e
er
r
o
r
(
MA
P
E
)
,
an
d
Md
A
E
.
Md
A
E
w
a
s
s
elec
ted
to
r
ep
r
esen
t
t
y
p
ical
er
r
o
r
u
n
d
er
s
p
ar
s
e
an
d
ze
r
o
-
in
f
lated
d
e
m
a
n
d
co
n
d
itio
n
s
[
2
6
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
24
,
No
.
4
,
A
u
g
u
s
t
20
26
:
1
287
-
1
2
9
3
1290
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
F
e
a
t
ure
eng
ineering
o
ut
co
m
e
a
nd
m
o
del per
f
o
r
m
a
nc
e
Fo
llo
w
i
n
g
t
h
e
f
ea
tu
r
e
e
n
g
in
e
er
in
g
p
r
o
ce
s
s
d
e
s
cr
ib
ed
in
t
h
e
me
t
h
o
d
s
ec
tio
n
,
T
ab
le
2
p
r
esen
t
s
t
h
e
f
i
n
al
s
et
o
f
f
ea
t
u
r
es
u
s
ed
f
o
r
m
ac
h
in
e
lear
n
i
n
g
m
o
d
eli
n
g
.
T
h
e
co
n
s
tr
u
cted
f
ea
t
u
r
es
r
ep
r
esen
t
ite
m
id
en
ti
t
y
,
b
asic
te
m
p
o
r
al
in
f
o
r
m
at
io
n
,
a
n
d
s
h
o
r
t
-
ter
m
d
e
m
a
n
d
d
y
n
a
m
i
cs
d
er
iv
ed
f
r
o
m
h
i
s
to
r
ical
u
s
a
g
e
an
d
p
r
o
cu
r
e
m
e
n
t
d
ata.
L
ag
g
ed
u
s
ag
e
a
n
d
p
u
r
ch
ase
v
ar
iab
les
p
r
o
v
id
e
lo
ca
lized
tem
p
o
r
al
s
ig
n
als,
w
h
ile
r
o
llin
g
a
v
er
ag
es
o
f
f
er
a
s
m
o
o
th
ed
r
ep
r
ese
n
tatio
n
o
f
r
ec
en
t
d
e
m
a
n
d
i
n
te
n
s
it
y
.
T
o
g
eth
er
,
th
e
s
e
f
ea
t
u
r
es
e
n
ab
le
t
h
e
g
lo
b
al
XGB
o
o
s
t
m
o
d
el
to
g
e
n
er
alize
ac
r
o
s
s
it
e
m
s
w
it
h
li
m
ited
h
i
s
to
r
ical
o
b
s
er
v
atio
n
s
,
w
h
ic
h
is
ess
e
n
tia
l
u
n
d
er
s
p
ar
s
e
an
d
ze
r
o
-
in
f
lated
d
e
m
a
n
d
co
n
d
itio
n
s
.
T
ab
le
2
.
Fin
al
f
ea
t
u
r
e
s
et
f
o
r
m
ac
h
in
e
lear
n
i
n
g
m
o
d
elin
g
F
e
a
t
u
r
e
D
e
scri
p
t
i
o
n
I
t
e
m
sp
a
r
e
p
a
r
t
U
n
i
q
u
e
i
d
e
n
t
i
f
i
e
r
o
f
t
h
e
sp
a
r
e
p
a
r
t
s
i
t
e
m
M
o
n
t
h
M
o
n
t
h
i
n
d
e
x
c
o
v
e
r
i
n
g
a
si
x
-
y
e
a
r
p
e
r
i
o
d
Y
e
a
r
Y
e
a
r
i
n
d
e
x
c
o
v
e
r
i
n
g
a
si
x
-
y
e
a
r
p
e
r
i
o
d
S
p
a
r
e
p
a
r
t
u
sag
e
M
o
n
t
h
l
y
sp
a
r
e
p
a
r
t
s
u
sag
e
o
v
e
r
a
si
x
-
y
e
a
r
p
e
r
i
o
d
L
a
g
1
sp
a
r
e
p
a
r
t
u
s
a
g
e
S
p
a
r
e
p
a
r
t
s
u
sag
e
o
n
e
mo
n
t
h
p
r
i
o
r
L
a
g
2
sp
a
r
e
p
a
r
t
u
s
a
g
e
S
p
a
r
e
p
a
r
t
s
u
sag
e
t
w
o
mo
n
t
h
s
p
r
i
o
r
R
o
l
l
i
n
g
2
s
p
a
r
e
p
a
r
t
u
sag
e
R
o
l
l
i
n
g
a
v
e
r
a
g
e
o
f
sp
a
r
e
p
a
r
t
s
u
s
a
g
e
o
v
e
r
t
h
e
p
r
e
v
i
o
u
s t
w
o
mo
n
t
h
s (L
a
g
1
a
n
d
L
a
g
2
)
S
p
a
r
e
p
a
r
t
p
u
r
c
h
a
se
d
M
o
n
t
h
l
y
sp
a
r
e
p
a
r
t
s
p
u
r
c
h
a
se
q
u
a
n
t
i
t
y
o
v
e
r
a
si
x
-
y
e
a
r
p
e
r
i
o
d
L
a
g
1
sp
a
r
e
p
a
r
t
p
u
r
c
h
a
se
d
S
p
a
r
e
p
a
r
t
s
p
u
r
c
h
a
se
q
u
a
n
t
i
t
y
o
n
e
mo
n
t
h
p
r
i
o
r
L
a
g
2
sp
a
r
e
p
a
r
t
p
u
r
c
h
a
se
d
S
p
a
r
e
p
a
r
t
s
p
u
r
c
h
a
se
q
u
a
n
t
i
t
y
t
w
o
mo
n
t
h
s
p
r
i
o
r
R
o
l
l
i
n
g
2
s
p
a
r
e
p
a
r
t
p
u
r
c
h
a
se
d
R
o
l
l
i
n
g
a
v
e
r
a
g
e
o
f
sp
a
r
e
p
a
r
t
s
p
u
r
c
h
a
se
q
u
a
n
t
i
t
y
o
v
e
r
t
h
e
p
r
e
v
i
o
u
s
t
w
o
mo
n
t
h
s
(
L
a
g
1
a
n
d
L
a
g
2
)
3
.
1
.
1
.
M
o
del
p
er
f
o
rm
a
nce
Glo
b
al
an
d
s
in
g
le
-
ite
m
XGB
o
o
s
t
m
o
d
els
w
er
e
tr
ain
ed
u
s
in
g
d
ata
f
r
o
m
2
0
2
0
to
2
0
2
4
an
d
ev
alu
a
ted
o
n
o
u
t
-
of
-
s
a
m
p
le
d
e
m
a
n
d
in
2
0
2
5
.
A
cr
o
s
s
all
ev
al
u
atio
n
m
e
tr
ics,
th
e
g
lo
b
al
m
o
d
el
co
n
s
is
t
en
tl
y
o
u
tp
er
f
o
r
m
ed
th
e
s
i
n
g
le
-
ite
m
m
o
d
el.
As
r
ep
o
r
ted
in
T
ab
le
3
,
th
e
g
lo
b
al
m
o
d
el
ac
h
ie
v
ed
s
u
b
s
ta
n
tial
l
y
lo
w
er
M
A
E
(
0
.
0
1
6
2
v
s
.
0
.
1
9
8
0
)
,
R
MSE
(
0
.
1
3
3
6
v
s
.
0
.
3
5
3
8
)
,
an
d
M
A
P
E
(
7
.
9
0
%
v
s
.
2
9
.
4
1
%),
in
d
icatin
g
m
o
r
e
ac
cu
r
ate
a
v
er
ag
e
d
em
a
n
d
es
ti
m
atio
n
.
I
n
ad
d
itio
n
to
m
ea
n
-
b
ased
m
etr
ic
s
,
r
o
b
u
s
tn
e
s
s
u
n
d
er
s
p
ar
s
e
d
e
m
a
n
d
c
o
n
d
itio
n
s
is
f
u
r
th
er
r
ef
lecte
d
b
y
t
h
e
Md
A
E
.
Gi
v
e
n
t
h
e
ze
r
o
-
i
n
f
lated
n
a
tu
r
e
o
f
s
p
ar
e
-
p
ar
ts
d
e
m
a
n
d
,
w
h
er
e
m
a
n
y
o
b
s
er
v
atio
n
s
ar
e
clo
s
e
to
ze
r
o
,
M
d
A
E
p
r
o
v
id
es
a
m
o
r
e
r
ep
r
esen
tatio
n
m
ea
s
u
r
e
o
f
t
y
p
ical
p
r
ed
ictio
n
er
r
o
r
.
T
h
e
g
lo
b
al
m
o
d
el
attain
ed
a
m
ar
k
ed
l
y
lo
w
er
Md
A
E
(
0
.
0
0
0
1
8
)
c
o
m
p
ar
ed
to
th
e
s
in
g
le
-
ite
m
m
o
d
el
(
0
.
0
0
1
8
1
)
,
in
d
icati
n
g
g
r
ea
ter
s
tab
ilit
y
u
n
d
er
h
ig
h
l
y
i
n
ter
m
i
tt
en
t d
e
m
a
n
d
co
n
d
itio
n
s
.
T
ab
le
3
.
Me
tr
ic
ev
alu
atio
n
r
es
u
lts
M
e
t
r
i
c
e
v
a
l
u
a
t
i
o
n
G
l
o
b
a
l
m
o
d
e
l
S
i
n
g
l
e
-
i
t
e
m mo
d
e
l
M
A
E
0
.
0
1
6
1
6
0
.
1
9
8
0
4
R
M
S
E
0
.
1
3
3
6
4
0
.
3
5
3
7
8
M
A
P
E
7
.
9
0
3
0
7
2
9
.
4
1
1
9
5
M
d
A
E
0
.
0
0
0
1
8
0
.
0
0
1
8
1
T
h
ese
r
esu
lts
ar
e
f
u
r
th
er
ill
u
s
tr
ated
in
Fig
u
r
e
2
,
w
h
ic
h
co
m
p
ar
e
s
ac
tu
al
s
p
ar
e
-
p
ar
ts
u
s
a
g
e
in
2
0
2
5
w
it
h
f
o
r
ec
ast
s
g
en
er
ated
b
y
b
o
th
m
o
d
elin
g
s
tr
ateg
ie
s
.
T
h
e
g
lo
b
al
m
o
d
el
s
h
o
w
s
clo
s
er
alig
n
m
en
t
w
it
h
o
b
s
er
v
ed
d
em
a
n
d
ac
r
o
s
s
m
o
s
t
ite
m
s
,
w
h
ile
t
h
e
s
i
n
g
le
-
ite
m
m
o
d
el
e
x
h
ib
its
lar
g
er
d
ev
iat
io
n
s
,
p
ar
ticu
lar
l
y
f
o
r
lo
w
-
u
s
a
g
e
an
d
h
i
g
h
l
y
i
n
ter
m
i
tten
t
i
te
m
s
.
O
v
er
all,
t
h
e
f
in
d
i
n
g
s
i
n
d
icate
t
h
at
t
h
e
g
lo
b
al
m
o
d
eli
n
g
ap
p
r
o
ac
h
p
r
o
v
id
es
m
o
r
e
ac
cu
r
ate
an
d
s
t
ab
le
f
o
r
ec
asts
u
n
d
er
s
p
ar
s
e
d
em
an
d
co
n
d
itio
n
s
.
3
.
2
.
Dis
cus
s
io
n
B
ef
o
r
e
d
is
cu
s
s
i
n
g
t
h
e
i
m
p
lica
tio
n
s
o
f
m
o
d
el
p
er
f
o
r
m
a
n
ce
,
it
is
u
s
ef
u
l
to
clar
if
y
h
o
w
th
e
en
g
i
n
ee
r
ed
f
ea
t
u
r
es
co
n
tr
ib
u
te
to
th
e
f
o
r
e
ca
s
tin
g
r
e
s
u
l
ts
.
T
h
e
co
m
b
i
n
ati
o
n
o
f
ite
m
id
en
t
if
ier
s
,
ti
m
e
-
r
el
ated
in
d
icato
r
s
,
a
n
d
s
h
o
r
t
-
ter
m
lag
an
d
r
o
llin
g
f
e
atu
r
es
en
ab
les
th
e
g
lo
b
al
m
o
d
el
to
ca
p
tu
r
e
b
o
th
s
i
m
ilar
iti
es
ac
r
o
s
s
ite
m
s
an
d
r
ec
en
t
d
e
m
a
n
d
b
eh
av
io
r
u
n
d
e
r
s
p
ar
s
e
co
n
d
itio
n
s
.
L
a
g
g
ed
u
s
ag
e
a
n
d
p
r
o
cu
r
e
m
e
n
t
f
ea
tu
r
e
s
p
r
o
v
id
e
lo
ca
lized
te
m
p
o
r
al
s
ig
n
a
ls
,
w
h
ile
r
o
llin
g
av
er
ag
e
s
h
elp
s
m
o
o
th
ir
r
eg
u
lar
f
lu
c
tu
at
io
n
s
t
h
at
ar
e
ty
p
i
ca
l
o
f
in
ter
m
itte
n
t
d
em
a
n
d
.
T
o
g
eth
er
,
t
h
ese
f
ea
tu
r
e
r
ep
r
esen
tat
io
n
s
s
u
p
p
o
r
t
m
o
r
e
e
f
f
ec
tiv
e
g
e
n
er
aliza
ti
o
n
w
h
en
h
i
s
to
r
ical
o
b
s
er
v
atio
n
s
ar
e
li
m
ited
,
w
h
ic
h
is
r
ef
lecte
d
in
t
h
e
s
u
p
er
io
r
p
er
f
o
r
m
an
ce
o
f
th
e
g
lo
b
al
m
o
d
el.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
X
GB
o
o
s
t m
o
d
elin
g
fo
r
s
p
a
r
s
e
s
p
a
r
e
-
p
a
r
ts
d
ema
n
d
fo
r
ec
a
s
tin
g
(
B
r
ia
n
Qa
ed
i La
kso
n
o
P
u
tr
a
)
1291
Fig
u
r
e
2
.
C
o
m
p
ar
is
o
n
o
f
g
lo
b
al
an
d
s
in
g
le
-
ite
m
m
o
d
eli
n
g
s
t
r
ateg
ies
f
o
r
s
p
ar
s
e
s
p
ar
e
p
ar
ts
d
em
a
n
d
T
h
e
s
u
p
er
io
r
p
er
f
o
r
m
an
ce
o
f
th
e
g
lo
b
al
m
o
d
el
ca
n
b
e
att
r
ib
u
ted
to
its
a
b
ilit
y
to
lev
er
ag
e
s
h
ar
ed
te
m
p
o
r
al
s
tr
u
ctu
r
e
s
an
d
cr
o
s
s
-
ite
m
d
e
m
an
d
ch
ar
ac
ter
is
t
ics.
B
y
p
o
o
lin
g
in
f
o
r
m
atio
n
ac
r
o
s
s
m
u
ltip
le
s
p
ar
e
-
p
ar
ts
item
s
,
th
e
g
lo
b
al
m
o
d
el
is
ab
le
to
ca
p
tu
r
e
w
ea
k
b
u
t
co
n
s
i
s
te
n
t
d
em
a
n
d
s
ig
n
al
s
th
at
ar
e
d
if
f
icu
l
t
to
lear
n
w
h
e
n
m
o
d
els
ar
e
tr
ain
ed
in
d
ep
en
d
en
tl
y
f
o
r
ea
ch
ite
m
.
I
n
c
o
n
tr
ast,
s
i
n
g
le
-
ite
m
m
o
d
el
s
r
el
y
s
o
lel
y
o
n
ite
m
-
s
p
ec
if
ic
h
i
s
to
r
ies
a
n
d
ar
e
t
h
er
ef
o
r
e
m
o
r
e
s
u
s
ce
p
tib
le
to
o
v
e
r
f
itti
n
g
an
d
u
n
s
tab
le
p
ar
a
m
ete
r
es
ti
m
atio
n
w
h
e
n
d
ata
ar
e
lim
ited
.
T
h
is
f
in
d
i
n
g
is
co
n
s
is
ten
t
w
it
h
p
r
io
r
s
tu
d
ies
o
n
g
lo
b
al
ti
m
e
-
s
er
ies
f
o
r
ec
a
s
tin
g
m
o
d
els,
w
h
ich
h
ig
h
li
g
h
t
th
e
b
en
e
f
i
ts
o
f
cr
o
s
s
-
s
er
ie
s
lear
n
i
n
g
u
n
d
er
s
p
ar
s
e
an
d
h
eter
o
g
e
n
eo
u
s
d
e
m
an
d
co
n
d
itio
n
s
[
1
0
]
,
[
1
5
]
.
Fro
m
an
o
p
er
atio
n
al
s
tan
d
p
o
in
t,
i
m
p
r
o
v
ed
f
o
r
ec
ast
s
tab
ilit
y
i
s
p
ar
ticu
lar
l
y
r
elev
a
n
t
f
o
r
cr
itical
s
p
ar
e
p
a
r
ts
w
it
h
lo
w
u
s
a
g
e
f
r
eq
u
e
n
c
y
.
M
o
r
e
r
eliab
le
d
em
a
n
d
esti
m
ates
ca
n
r
ed
u
ce
t
h
e
te
n
d
en
c
y
to
war
d
ex
ce
s
s
i
v
e
s
a
f
et
y
s
to
ck
w
h
ile
s
u
p
p
o
r
tin
g
ti
m
e
l
y
r
ep
len
is
h
m
e
n
t
d
ec
is
i
o
n
s
d
u
r
in
g
u
n
p
lan
n
ed
m
ai
n
te
n
an
ce
ev
en
t
s
.
T
h
is
is
esp
ec
iall
y
i
m
p
o
r
tan
t
f
o
r
s
lo
w
-
m
o
v
i
n
g
a
n
d
h
i
g
h
-
v
al
u
e
s
p
ar
e
p
ar
ts
,
w
h
er
e
b
o
th
o
v
er
s
to
c
k
in
g
a
n
d
s
to
ck
-
o
u
t
r
is
k
s
ca
r
r
y
s
ig
n
i
f
ica
n
t
o
p
er
atio
n
al
an
d
f
i
n
an
c
ial
co
n
s
eq
u
e
n
c
es.
A
m
o
r
e
d
etailed
a
n
al
y
s
i
s
o
f
ite
m
-
le
v
el
f
ail
u
r
e
ca
s
es
a
n
d
ex
p
lici
t
co
s
t
q
u
an
t
if
icatio
n
i
s
le
f
t
f
o
r
f
u
t
u
r
e
w
o
r
k
,
as
it
r
eq
u
ir
es
ad
d
itio
n
al
o
p
er
atio
n
al
d
ata
b
e
y
o
n
d
th
e
s
co
p
e
o
f
th
i
s
s
t
u
d
y
.
A
lt
h
o
u
g
h
t
h
e
g
lo
b
al
m
o
d
eli
n
g
ap
p
r
o
ac
h
co
n
s
is
ten
tl
y
o
u
tp
er
f
o
r
m
s
th
e
s
i
n
g
le
-
ite
m
m
o
d
el
o
n
av
er
a
g
e,
its
ef
f
ec
ti
v
e
n
ess
v
ar
ies
w
it
h
th
e
d
eg
r
ee
o
f
d
e
m
an
d
s
p
ar
s
it
y
.
Fo
r
ite
m
s
w
it
h
m
o
d
er
ate
s
p
ar
s
it
y
,
w
h
er
e
o
cc
asio
n
al
n
o
n
-
ze
r
o
d
e
m
a
n
d
p
r
o
v
id
es
in
f
o
r
m
ati
v
e
s
ig
n
al
s
,
g
l
o
b
al
m
o
d
eli
n
g
b
e
n
ef
its
f
r
o
m
c
r
o
s
s
-
ite
m
lear
n
i
n
g
an
d
p
r
o
d
u
ce
s
m
o
r
e
s
tab
le
f
o
r
ec
asts
.
Ho
w
e
v
er
,
f
o
r
ite
m
s
ex
h
ib
i
ti
n
g
e
x
tr
e
m
e
s
p
ar
s
it
y
,
ch
ar
ac
ter
ized
b
y
p
r
o
lo
n
g
ed
s
eq
u
e
n
ce
s
o
f
ze
r
o
d
e
m
an
d
a
n
d
v
er
y
l
i
m
ited
n
o
n
-
ze
r
o
o
b
s
er
v
atio
n
s
,
t
h
e
ad
v
an
ta
g
e
o
f
g
lo
b
al
m
o
d
eli
n
g
b
ec
o
m
es
le
s
s
p
r
o
n
o
u
n
ce
d
.
I
n
s
u
c
h
ca
s
e
s
,
b
o
th
g
lo
b
al
an
d
s
in
g
le
-
ite
m
m
o
d
els
te
n
d
to
g
en
er
ate
n
ea
r
-
ze
r
o
f
o
r
ec
a
s
ts
,
r
esu
lti
n
g
i
n
s
i
m
ilar
p
r
ed
ictiv
e
p
er
f
o
r
m
a
n
ce
.
Un
d
er
th
ese
co
n
d
it
io
n
s
,
p
er
ce
n
tag
e
-
b
ased
er
r
o
r
m
ea
s
u
r
es
s
u
ch
as
M
A
P
E
ar
e
o
n
l
y
in
f
o
r
m
a
tiv
e
d
u
r
i
n
g
n
o
n
-
z
er
o
d
em
an
d
p
er
io
d
s
,
w
h
ile
ab
s
o
lu
te
-
er
r
o
r
m
etr
ics
p
r
o
v
id
e
a
m
o
r
e
co
n
s
is
te
n
t
i
n
d
icatio
n
o
f
m
o
d
el
b
eh
a
v
io
r
ac
r
o
s
s
h
i
g
h
l
y
s
p
ar
s
e
s
er
ies.
T
h
is
l
i
m
i
tatio
n
u
n
d
er
ex
tr
e
m
e
s
p
ar
s
it
y
i
s
also
co
n
s
is
ten
t
w
it
h
f
in
d
i
n
g
s
i
n
in
ter
m
itte
n
t
-
d
e
m
a
n
d
f
o
r
ec
asti
n
g
l
iter
atu
r
e
[
3
]
.
T
h
ese
o
b
s
er
v
atio
n
s
h
i
g
h
li
g
h
t
p
o
ten
tial
f
ailu
r
e
s
ce
n
ar
io
s
f
o
r
g
lo
b
al
m
o
d
elin
g
,
p
ar
ticu
l
ar
l
y
w
h
e
n
d
em
a
n
d
i
n
f
o
r
m
atio
n
is
i
n
s
u
f
f
icien
t
e
v
e
n
af
ter
p
o
o
lin
g
d
at
a
ac
r
o
s
s
ite
m
s
.
U
n
d
er
ex
tr
e
m
e
s
p
ar
s
it
y
,
s
h
ar
ed
p
atter
n
s
ac
r
o
s
s
ite
m
s
p
r
o
v
id
e
li
m
ited
ad
d
itio
n
al
g
u
id
an
ce
,
an
d
th
e
g
lo
b
al
m
o
d
el
m
a
y
o
f
f
er
o
n
l
y
m
ar
g
i
n
al
i
m
p
r
o
v
e
m
en
t
o
v
er
ite
m
-
s
p
ec
i
f
ic
ap
p
r
o
ac
h
es.
T
h
is
li
m
itatio
n
s
u
g
g
est
s
t
h
at
t
h
e
b
en
e
f
i
ts
o
f
g
lo
b
al
lear
n
i
n
g
ar
e
m
o
s
t e
v
id
en
t
w
h
e
n
s
p
ar
s
e
d
e
m
an
d
s
till
co
n
tain
s
w
ea
k
b
u
t in
f
o
r
m
at
iv
e
te
m
p
o
r
al
s
ig
n
al
s
.
Fro
m
a
p
r
ac
tical
s
tan
d
p
o
in
t,
i
m
p
r
o
v
e
m
e
n
ts
i
n
f
o
r
ec
asti
n
g
ac
cu
r
ac
y
a
n
d
s
tab
ilit
y
h
a
v
e
d
ir
ec
t
i
m
p
licatio
n
s
f
o
r
i
n
v
e
n
to
r
y
d
ec
is
io
n
-
m
ak
i
n
g
.
L
o
w
er
t
y
p
ica
l
f
o
r
ec
asti
n
g
er
r
o
r
s
r
ed
u
ce
u
n
ce
r
tain
t
y
i
n
d
e
m
a
n
d
esti
m
ates,
w
h
ic
h
ca
n
h
e
lp
p
r
e
v
en
t
e
x
ce
s
s
iv
e
s
a
f
et
y
s
to
ck
al
lo
ca
tio
n
,
p
ar
ticu
lar
l
y
f
o
r
s
lo
w
-
m
o
v
i
n
g
a
n
d
h
ig
h
-
v
alu
e
s
p
ar
e
p
ar
ts
.
Mo
r
e
s
tab
le
f
o
r
ec
asts
also
s
u
p
p
o
r
t
b
et
ter
tim
in
g
o
f
r
ep
len
i
s
h
m
e
n
t
d
ec
is
io
n
s
,
th
er
eb
y
lo
w
er
i
n
g
i
n
v
e
n
to
r
y
h
o
ld
in
g
co
s
ts
an
d
r
ed
u
cin
g
th
e
r
is
k
o
f
o
b
s
o
lescen
ce
.
T
h
ese
f
in
d
i
n
g
s
ar
e
co
n
s
is
te
n
t
w
ith
p
r
io
r
r
esear
ch
o
n
in
ter
m
itte
n
t
-
d
em
a
n
d
in
v
e
n
to
r
y
co
n
tr
o
l a
n
d
s
p
ar
e
-
p
ar
ts
m
a
n
a
g
e
m
e
n
t
[
5
]
.
I
n
ad
d
itio
n
,
i
m
p
r
o
v
ed
f
o
r
ec
as
t
r
eliab
ilit
y
co
n
tr
ib
u
te
s
to
s
er
v
ice
le
v
el
p
er
f
o
r
m
a
n
ce
b
y
r
e
d
u
cin
g
t
h
e
lik
eli
h
o
o
d
o
f
s
to
ck
o
u
ts
d
u
r
in
g
u
n
p
lan
n
ed
m
ain
ten
a
n
ce
e
v
e
n
ts
.
W
h
ile
t
h
is
s
tu
d
y
d
o
es
n
o
t
ex
p
licitl
y
q
u
a
n
ti
f
y
co
s
t
s
av
i
n
g
s
o
r
s
er
v
ice
lev
el
im
p
r
o
v
e
m
e
n
t
s
,
th
e
o
b
s
er
v
ed
r
e
d
u
ctio
n
in
f
o
r
ec
asti
n
g
er
r
o
r
s
s
u
g
g
es
ts
m
ea
n
i
n
g
f
u
l
p
o
ten
tial
b
en
ef
its
i
n
ter
m
s
o
f
in
v
e
n
to
r
y
e
f
f
icien
c
y
,
s
a
f
et
y
s
to
ck
o
p
ti
m
izat
io
n
,
an
d
o
p
er
atio
n
al
r
eliab
ilit
y
i
n
in
d
u
s
t
r
ial
m
a
in
te
n
a
n
ce
en
v
ir
o
n
m
e
n
t
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
24
,
No
.
4
,
A
u
g
u
s
t
20
26
:
1
287
-
1
2
9
3
1292
4.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
s
h
o
w
s
t
h
at
g
lo
b
al
XGB
o
o
s
t
m
o
d
eli
n
g
p
r
o
v
id
es
m
o
r
e
ac
cu
r
ate
an
d
r
o
b
u
s
t
f
o
r
e
ca
s
ts
th
a
n
s
in
g
le
-
ite
m
m
o
d
eli
n
g
u
n
d
er
s
p
ar
s
e
an
d
in
ter
m
itten
t
s
p
ar
e
-
p
ar
ts
d
e
m
a
n
d
co
n
d
itio
n
s
.
B
y
lear
n
in
g
s
h
ar
ed
d
em
a
n
d
p
atter
n
s
ac
r
o
s
s
m
u
lti
p
le
item
s
,
th
e
g
lo
b
al
m
o
d
el
co
n
s
is
ten
tl
y
ac
h
ie
v
es
lo
w
er
av
er
ag
e
an
d
t
y
p
ical
er
r
o
r
s
ac
r
o
s
s
all
ev
alu
a
tio
n
m
etr
ics,
in
cl
u
d
in
g
Md
A
E
.
Fro
m
a
p
r
ac
tical
p
er
s
p
ec
tiv
e,
th
e
i
m
p
r
o
v
ed
s
tab
ilit
y
o
f
g
lo
b
al
f
o
r
ec
asts
s
u
p
p
o
r
ts
m
o
r
e
r
eliab
le
in
v
e
n
to
r
y
p
la
n
n
in
g
b
y
r
ed
u
c
in
g
u
n
ce
r
tai
n
t
y
i
n
p
r
o
cu
r
e
m
e
n
t
d
ec
is
io
n
s
.
T
h
is
ca
n
h
e
lp
o
r
g
an
izatio
n
s
b
alan
ce
s
p
ar
e
-
p
ar
ts
a
v
ailab
ilit
y
w
it
h
i
n
v
e
n
to
r
y
h
o
ld
in
g
co
s
ts
,
p
ar
ticu
lar
l
y
f
o
r
cr
itical
an
d
s
lo
w
-
m
o
v
i
n
g
ite
m
s
.
Ov
er
all,
g
lo
b
al
m
o
d
eli
n
g
o
f
f
er
s
a
s
ca
lab
le
an
d
d
ata
-
e
f
f
ic
ien
t
f
o
u
n
d
atio
n
f
o
r
in
ter
m
itte
n
t
-
d
e
m
a
n
d
f
o
r
ec
asti
n
g
in
i
n
d
u
s
tr
ial
i
n
v
en
to
r
y
s
y
s
te
m
s
.
B
e
y
o
n
d
s
p
ar
e
-
p
ar
ts
ap
p
licatio
n
s
,
th
e
p
r
o
p
o
s
ed
g
lo
b
al
m
o
d
elin
g
f
r
am
e
w
o
r
k
is
also
ap
p
licab
le
to
o
th
er
s
p
ar
s
e
-
d
e
m
a
n
d
f
o
r
ec
asti
n
g
d
o
m
ai
n
s
,
s
u
c
h
as
en
er
g
y
co
n
s
u
m
p
tio
n
,
r
etai
l in
v
en
to
r
y
m
an
a
g
e
m
e
n
t,
an
d
I
o
T
-
en
ab
led
s
y
s
te
m
s
.
F
u
t
u
r
e
r
esea
r
ch
m
a
y
e
x
te
n
d
th
i
s
w
o
r
k
b
y
in
co
r
p
o
r
atin
g
lo
n
g
er
h
is
to
r
ical
d
atasets
,
m
u
l
ti
-
in
d
u
s
tr
y
v
alid
atio
n
,
r
o
llin
g
-
o
r
ig
in
ev
alu
a
tio
n
,
an
d
th
e
in
te
g
r
atio
n
o
f
tr
an
s
f
er
lear
n
i
n
g
a
n
d
ex
p
lai
n
ab
le
m
ac
h
i
n
e
-
le
ar
n
in
g
tec
h
n
iq
u
e
s
to
f
u
r
t
h
er
e
n
h
a
n
ce
r
o
b
u
s
tn
e
s
s
an
d
in
ter
p
r
etab
ilit
y
.
F
UNDIN
G
I
NF
O
RM
AT
I
O
N
Au
t
h
o
r
s
s
tate
n
o
f
u
n
d
i
n
g
i
n
v
o
l
v
ed
.
AUTHO
R
CO
NT
RIB
UT
I
O
NS ST
A
T
E
M
E
NT
T
h
is
j
o
u
r
n
al
u
s
e
s
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT
)
to
r
ec
o
g
n
ize
in
d
i
v
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
t
h
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
lla
b
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
B
r
ian
Qae
d
i L
ak
s
o
n
o
P
u
tr
a
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
J
er
r
y
D
w
i T
r
ijo
y
o
P
u
r
n
o
m
o
✓
✓
✓
✓
✓
✓
C
:
C
o
n
ce
p
tu
aliza
t
io
n
M
:
M
eth
o
d
o
lo
g
y
So
:
So
f
t
w
ar
e
Va
:
Va
lid
atio
n
Fo
:
Fo
r
m
al
a
n
al
y
s
i
s
I
:
I
n
v
est
ig
atio
n
R
:
R
eso
u
r
ce
s
D
:
D
ata
C
u
r
atio
n
O
:
W
r
itin
g
-
O
r
ig
i
n
al
Dr
a
f
t
E
:
W
r
itin
g
-
R
e
v
ie
w
&
E
d
iti
n
g
Vi
:
Vi
s
u
a
lizatio
n
Su
:
Su
p
er
v
is
io
n
P
:
P
r
o
j
ec
t a
d
m
i
n
is
tr
atio
n
Fu
:
Fu
n
d
in
g
ac
q
u
i
s
itio
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
t
h
o
r
s
s
tate
n
o
co
n
f
lic
t o
f
i
n
t
er
est.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
th
at
s
u
p
p
o
r
t
th
e
f
i
n
d
in
g
s
o
f
t
h
is
s
t
u
d
y
ar
e
a
v
aila
b
le
f
r
o
m
t
h
e
co
r
r
esp
o
n
d
in
g
a
u
th
o
r
u
p
o
n
r
ea
s
o
n
ab
le
r
eq
u
est.
RE
F
E
R
E
NC
E
S
[
1
]
K
.
B
a
n
d
a
r
a
,
C
.
B
e
r
g
me
i
r
,
a
n
d
S
.
S
m
y
l
,
“
F
o
r
e
c
a
st
i
n
g
a
c
r
o
ss
t
i
me
se
r
i
e
s
d
a
t
a
b
a
se
s
u
s
i
n
g
r
e
c
u
r
r
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
s
o
n
g
r
o
u
p
s
o
f
si
mi
l
a
r
se
r
i
e
s:
A
c
l
u
st
e
r
i
n
g
a
p
p
r
o
a
c
h
,
”
Ex
p
e
r
t
S
y
st
e
m
s
w
i
t
h
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
4
0
,
p
.
1
1
2
8
9
6
,
F
e
b
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
1
9
.
1
1
2
8
9
6
.
[
2
]
P
.
M
o
n
t
e
r
o
-
M
a
n
so
a
n
d
R
.
J.
H
y
n
d
m
a
n
,
“
P
r
i
n
c
i
p
l
e
s
a
n
d
a
l
g
o
r
i
t
h
ms
f
o
r
f
o
r
e
c
a
st
i
n
g
g
r
o
u
p
s
o
f
t
i
me
se
r
i
e
s:
L
o
c
a
l
i
t
y
a
n
d
g
l
o
b
a
l
i
t
y
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
F
o
re
c
a
s
t
i
n
g
,
v
o
l
.
3
7
,
n
o
.
4
,
p
p
.
1
6
3
2
–
1
6
5
3
,
O
c
t
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
j
f
o
r
e
c
a
st
.
2
0
2
1
.
0
3
.
0
0
4
.
[
3
]
M
.
Z
.
B
a
b
a
i
,
A
.
S
y
n
t
e
t
o
s,
a
n
d
R
.
T
e
u
n
t
e
r
,
“
I
n
t
e
rm
i
t
t
e
n
t
d
e
m
a
n
d
f
o
r
e
c
a
s
t
i
n
g
:
A
n
e
m
p
i
r
i
c
a
l
st
u
d
y
o
n
a
c
c
u
r
a
c
y
a
n
d
t
h
e
ri
sk
o
f
o
b
s
o
l
e
sc
e
n
c
e
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
Jo
u
r
n
a
l
o
f
P
r
o
d
u
c
t
i
o
n
Ec
o
n
o
mi
c
s
,
v
o
l
.
1
5
7
,
p
p
.
2
1
2
–
2
1
9
,
N
o
v
.
2
0
1
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
j
p
e
.
2
0
1
4
.
0
8
.
0
1
9
.
[
4
]
R
.
H
.
T
e
u
n
t
e
r
,
A
.
A
.
S
y
n
t
e
t
o
s,
a
n
d
M
.
Z
i
e
d
B
a
b
a
i
,
“
I
n
t
e
r
mi
t
t
e
n
t
d
e
ma
n
d
:
L
i
n
k
i
n
g
f
o
r
e
c
a
st
i
n
g
t
o
i
n
v
e
n
t
o
r
y
o
b
so
l
e
sce
n
c
e
,
”
Eu
r
o
p
e
a
n
J
o
u
r
n
a
l
o
f
O
p
e
ra
t
i
o
n
a
l
R
e
s
e
a
r
c
h
,
v
o
l
.
2
1
4
,
n
o
.
3
,
p
p
.
6
0
6
–
6
1
5
,
N
o
v
.
2
0
1
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
j
o
r
.
2
0
1
1
.
0
5
.
0
1
8
.
[
5
]
A
.
A
.
S
y
n
t
e
t
o
s
a
n
d
J
.
E.
B
o
y
l
a
n
,
“
T
h
e
a
c
c
u
r
a
c
y
o
f
i
n
t
e
r
mi
t
t
e
n
t
d
e
man
d
e
st
i
ma
t
e
s,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Fo
r
e
c
a
st
i
n
g
,
v
o
l
.
2
1
,
n
o
.
2
,
p
p
.
3
0
3
–
3
1
4
,
A
p
r
.
2
0
0
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
j
f
o
r
e
c
a
st
.
2
0
0
4
.
1
0
.
0
0
1
.
[
6
]
S
.
M
a
k
r
i
d
a
k
i
s
,
E.
S
p
i
l
i
o
t
i
s,
a
n
d
V
.
A
ssi
ma
k
o
p
o
u
l
o
s,
“
S
t
a
t
i
st
i
c
a
l
a
n
d
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
f
o
r
e
c
a
st
i
n
g
me
t
h
o
d
s:
C
o
n
c
e
r
n
s
a
n
d
w
a
y
s
f
o
r
w
a
r
d
,
”
PL
o
S
O
N
E
,
v
o
l
.
1
3
,
n
o
.
3
,
p
.
e
0
1
9
4
8
8
9
,
M
a
r
.
2
0
1
8
,
d
o
i
:
1
0
.
1
3
7
1
/
j
o
u
r
n
a
l
.
p
o
n
e
.
0
1
9
4
8
8
9
.
[
7
]
T
.
C
h
e
n
a
n
d
C
.
G
u
e
st
r
i
n
,
“
X
G
B
o
o
s
t
:
A
sca
l
a
b
l
e
t
r
e
e
b
o
o
st
i
n
g
sy
st
e
m,”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
AC
M
S
I
G
K
D
D
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
K
n
o
w
l
e
d
g
e
D
i
sc
o
v
e
ry
a
n
d
D
a
t
a
Mi
n
i
n
g
,
N
e
w
Y
o
r
k
,
N
Y
,
U
S
A
:
A
C
M
,
A
u
g
.
2
0
1
6
,
p
p
.
7
8
5
–
7
9
4
.
d
o
i
:
1
0
.
1
1
4
5
/
2
9
3
9
6
7
2
.
2
9
3
9
7
8
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
X
GB
o
o
s
t m
o
d
elin
g
fo
r
s
p
a
r
s
e
s
p
a
r
e
-
p
a
r
ts
d
ema
n
d
fo
r
ec
a
s
tin
g
(
B
r
ia
n
Qa
ed
i La
kso
n
o
P
u
tr
a
)
1293
[
8
]
Y
.
W
a
n
g
,
S
.
S
u
n
,
X
.
C
h
e
n
,
X
.
Z
e
n
g
,
Y
.
K
o
n
g
,
J.
C
h
e
n
,
Y
.
G
u
o
,
a
n
d
T
.
W
a
n
g
,
“
S
h
o
r
t
-
t
e
r
m
l
o
a
d
f
o
r
e
c
a
st
i
n
g
o
f
i
n
d
u
st
r
i
a
l
c
u
s
t
o
me
r
s
b
a
se
d
o
n
S
V
M
D
a
n
d
X
G
B
o
o
st
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
E
l
e
c
t
ri
c
a
l
Po
w
e
r
&
En
e
r
g
y
S
y
st
e
m
s
,
v
o
l
.
1
2
9
,
p
.
1
0
6
8
3
0
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
j
e
p
e
s.2
0
2
1
.
1
0
6
8
3
0
.
[
9
]
L
.
S
e
mm
e
l
man
n
,
S
.
H
e
n
n
i
,
a
n
d
C
.
W
e
i
n
h
a
r
d
t
,
“
L
o
a
d
f
o
r
e
c
a
st
i
n
g
f
o
r
e
n
e
r
g
y
c
o
mm
u
n
i
t
i
e
s:
a
n
o
v
e
l
L
S
T
M
-
X
G
B
o
o
st
h
y
b
r
i
d
mo
d
e
l
b
a
se
d
o
n
sm
a
r
t
me
t
e
r
d
a
t
a
,
”
E
n
e
r
g
y
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
5
,
n
o
.
S
1
,
S
e
p
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
8
6
/
s
4
2
1
6
2
-
022
-
0
0
2
1
2
-
9.
[
1
0
]
H
.
H
e
w
a
mal
a
g
e
,
C
.
B
e
r
g
me
i
r
,
a
n
d
K
.
B
a
n
d
a
r
a
,
“
G
l
o
b
a
l
mo
d
e
l
s
f
o
r
t
i
me
se
r
i
e
s
f
o
r
e
c
a
st
i
n
g
:
A
S
i
mu
l
a
t
i
o
n
st
u
d
y
,
”
Pa
t
t
e
rn
Re
c
o
g
n
i
t
i
o
n
,
v
o
l
.
1
2
4
,
p
.
1
0
8
4
4
1
,
A
p
r
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
a
t
c
o
g
.
2
0
2
1
.
1
0
8
4
4
1
.
[
1
1
]
T
.
Jan
u
sc
h
o
w
sk
i
,
Y
.
W
a
n
g
,
K
.
T
o
r
k
k
o
l
a
,
T
.
Er
k
k
i
l
ä
,
H
.
H
a
sso
n
,
a
n
d
J
.
G
a
st
h
a
u
s
,
“
F
o
r
e
c
a
st
i
n
g
w
i
t
h
t
r
e
e
s,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Fo
r
e
c
a
st
i
n
g
,
v
o
l
.
3
8
,
n
o
.
4
,
p
p
.
1
4
7
3
–
1
4
8
1
,
O
c
t
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
j
f
o
r
e
c
a
st
.
2
0
2
1
.
1
0
.
0
0
4
.
[
1
2
]
H
.
P
a
t
i
l
,
B
.
K
.
B
o
l
l
a
,
E.
S
a
b
e
e
sh
,
a
n
d
D
.
R
.
B
h
u
mi
r
e
d
d
y
,
“
C
o
mp
a
r
a
t
i
v
e
S
t
u
d
y
o
f
P
r
e
d
i
c
t
i
n
g
S
t
o
c
k
I
n
d
e
x
U
si
n
g
D
e
e
p
L
e
a
r
n
i
n
g
M
o
d
e
l
s,”
L
e
c
t
u
re
N
o
t
e
s
o
f
t
h
e
I
n
st
i
t
u
t
e
f
o
r
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
s,
S
o
c
i
a
l
I
n
f
o
r
m
a
t
i
c
s
a
n
d
T
e
l
e
c
o
m
m
u
n
i
c
a
t
i
o
n
s E
n
g
i
n
e
e
ri
n
g
.
S
p
r
i
n
g
e
r
N
a
t
u
r
e
S
w
i
t
z
e
rl
a
n
d
,
p
p
.
4
5
–
5
7
,
2
0
2
4
.
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
031
-
4
8
8
8
8
-
7
_
4
.
[
1
3
]
D
.
S
a
l
i
n
a
s,
V
.
F
l
u
n
k
e
r
t
,
J
.
G
a
st
h
a
u
s
,
a
n
d
T
.
Ja
n
u
sc
h
o
w
sk
i
,
“
D
e
e
p
A
R
:
P
r
o
b
a
b
i
l
i
st
i
c
f
o
r
e
c
a
s
t
i
n
g
w
i
t
h
a
u
t
o
r
e
g
r
e
ssi
v
e
r
e
c
u
r
r
e
n
t
n
e
t
w
o
r
k
s,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
F
o
re
c
a
s
t
i
n
g
,
v
o
l
.
3
6
,
n
o
.
3
,
p
p
.
1
1
8
1
–
1
1
9
1
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
j
f
o
r
e
c
a
st
.
2
0
1
9
.
0
7
.
0
0
1
.
[
1
4
]
B
.
N
.
O
r
e
sh
k
i
n
,
D
.
C
a
r
p
o
v
,
N
.
C
h
a
p
a
d
o
s,
a
n
d
Y
.
B
e
n
g
i
o
,
“
N
-
B
EA
T
S
:
N
e
u
r
a
l
b
a
si
s
e
x
p
a
n
s
i
o
n
a
n
a
l
y
si
s
f
o
r
i
n
t
e
r
p
r
e
t
a
b
l
e
t
i
me
se
r
i
e
s fo
r
e
c
a
st
i
n
g
,
”
8
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
L
e
a
rn
i
n
g
Re
p
res
e
n
t
a
t
i
o
n
s
(
I
C
L
R
)
,
2
0
2
0
.
[
15]
B
.
L
i
m,
S
.
A
r
ı
k
,
N
.
L
o
e
f
f
,
a
n
d
T
.
P
f
i
s
t
e
r
,
“
Te
mp
o
r
a
l
F
u
si
o
n
T
r
a
n
sf
o
r
me
r
s
f
o
r
i
n
t
e
r
p
r
e
t
a
b
l
e
mu
l
t
i
-
h
o
r
i
z
o
n
t
i
me
se
r
i
e
s
f
o
r
e
c
a
st
i
n
g
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
F
o
re
c
a
s
t
i
n
g
,
v
o
l
.
3
7
,
n
o
.
4
,
p
p
.
1
7
4
8
–
1
7
6
4
,
O
c
t
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
j
f
o
r
e
c
a
st
.
2
0
2
1
.
0
3
.
0
1
2
.
[1
6]
K
.
B
e
n
i
d
i
s
e
t
a
l
.
,
“
D
e
e
p
L
e
a
r
n
i
n
g
f
o
r
T
i
me
S
e
r
i
e
s
F
o
r
e
c
a
st
i
n
g
:
T
u
t
o
r
i
a
l
a
n
d
L
i
t
e
r
a
t
u
r
e
S
u
r
v
e
y
,
”
AC
M
C
o
m
p
u
t
i
n
g
S
u
r
v
e
y
s
,
v
o
l
.
5
5
,
n
o
.
6
,
p
p
.
1
–
3
6
,
D
e
c
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
4
5
/
3
5
3
3
3
8
2
.
[
1
7
]
Ç
.
P
i
n
ç
e
,
L
.
T
u
r
r
i
n
i
,
a
n
d
J
.
M
e
i
ssn
e
r
,
“
I
n
t
e
r
mi
t
t
e
n
t
d
e
ma
n
d
f
o
r
e
c
a
st
i
n
g
f
o
r
sp
a
r
e
p
a
r
t
s:
A
C
r
i
t
i
c
a
l
r
e
v
i
e
w
,
”
O
m
e
g
a
(
U
n
i
t
e
d
K
i
n
g
d
o
m
)
,
v
o
l
.
1
0
5
,
p
.
1
0
2
5
1
3
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
o
me
g
a
.
2
0
2
1
.
1
0
2
5
1
3
.
[
1
8
]
S
.
S
.
R
a
n
g
a
p
u
r
a
m
,
M
.
W
.
S
e
e
g
e
r
,
J.
G
a
st
h
a
u
s,
L
.
S
t
e
l
l
a
,
Y
.
W
a
n
g
,
a
n
d
T
.
Jan
u
sc
h
o
w
sk
i
,
“
D
e
e
p
st
a
t
e
sp
a
c
e
mo
d
e
l
s
f
o
r
t
i
me
se
r
i
e
s
f
o
r
e
c
a
st
i
n
g
,
”
i
n
N
I
P
S
'
1
8
:
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
3
2
n
d
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
N
e
u
r
a
l
I
n
f
o
rm
a
t
i
o
n
Pr
o
c
e
ssi
n
g
S
y
st
e
m
s
(
N
e
u
rI
PS
)
,
M
o
n
t
r
é
a
l
,
C
a
n
a
d
a
,
2
0
1
8
,
p
p
.
7
7
9
6
–
7
8
0
5
.
[
1
9
]
L
.
F
a
n
,
X
.
L
i
u
,
W
.
M
a
o
,
K
.
Y
a
n
g
,
a
n
d
Z
.
S
o
n
g
,
“
S
p
a
r
e
P
a
r
t
s
D
e
ma
n
d
F
o
r
e
c
a
st
i
n
g
M
e
t
h
o
d
B
a
se
d
o
n
I
n
t
e
r
mi
t
t
e
n
t
F
e
a
t
u
r
e
A
d
a
p
t
a
t
i
o
n
,
”
E
n
t
r
o
p
y
,
v
o
l
.
2
5
,
n
o
.
5
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
e
2
5
0
5
0
7
6
4
.
[
2
0
]
W
.
W
a
n
g
a
n
d
A
.
A
.
S
y
n
t
e
t
o
s,
“
S
p
a
r
e
p
a
r
t
s
d
e
man
d
:
L
i
n
k
i
n
g
f
o
r
e
c
a
st
i
n
g
t
o
e
q
u
i
p
me
n
t
m
a
i
n
t
e
n
a
n
c
e
,
”
T
r
a
n
s
p
o
rt
a
t
i
o
n
Re
s
e
a
rc
h
Pa
rt
E:
L
o
g
i
st
i
c
s
a
n
d
T
r
a
n
s
p
o
rt
a
t
i
o
n
Re
v
i
e
w
,
v
o
l
.
4
7
,
n
o
.
6
,
p
p
.
1
1
9
4
–
1
2
0
9
,
N
o
v
.
2
0
1
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
t
r
e
.
2
0
1
1
.
0
4
.
0
0
8
.
[
2
1
]
S
.
X
i
e
e
t
a
l
.
,
“
A
D
e
e
p
A
R
-
B
a
se
d
M
o
d
e
l
i
n
g
F
r
a
mew
o
r
k
f
o
r
P
r
o
b
a
b
i
l
i
s
t
i
c
M
i
d
–
L
o
n
g
-
Te
r
m
S
t
r
e
a
mf
l
o
w
P
r
e
d
i
c
t
i
o
n
,
”
W
a
t
e
r
,
v
o
l
.
1
7
,
n
o
.
1
7
,
p
.
2
5
0
6
,
A
u
g
.
2
0
2
5
,
d
o
i
:
1
0
.
3
3
9
0
/
w
1
7
1
7
2
5
0
6
.
[
2
2
]
O
.
B
.
S
e
z
e
r
,
M
.
U
.
G
u
d
e
l
e
k
,
a
n
d
A
.
M
.
O
z
b
a
y
o
g
l
u
,
“
F
i
n
a
n
c
i
a
l
t
i
me
se
r
i
e
s
f
o
r
e
c
a
st
i
n
g
w
i
t
h
d
e
e
p
l
e
a
r
n
i
n
g
:
A
sy
st
e
mat
i
c
l
i
t
e
r
a
t
u
r
e
r
e
v
i
e
w
:
2
0
0
5
–
2
0
1
9
,
”
Ap
p
l
i
e
d
S
o
f
t
C
o
m
p
u
t
i
n
g
J
o
u
rn
a
l
,
v
o
l
.
9
0
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
so
c
.
2
0
2
0
.
1
0
6
1
8
1
.
[
2
3
]
F
.
P
e
t
r
o
p
o
u
l
o
s
a
n
d
N
.
K
o
u
r
e
n
t
z
e
s,
“
F
o
r
e
c
a
st
c
o
m
b
i
n
a
t
i
o
n
s
f
o
r
i
n
t
e
r
mi
t
t
e
n
t
d
e
man
d
,
”
J
o
u
r
n
a
l
o
f
t
h
e
O
p
e
r
a
t
i
o
n
a
l
R
e
se
a
rc
h
S
o
c
i
e
t
y
,
v
o
l
.
6
6
,
n
o
.
6
,
p
p
.
9
1
4
–
9
2
4
,
2
0
1
5
,
d
o
i
:
1
0
.
1
0
5
7
/
j
o
r
s.2
0
1
4
.
6
2
.
[
2
4
]
C
.
B
e
r
g
me
i
r
,
R
.
J.
H
y
n
d
ma
n
,
a
n
d
B
.
K
o
o
,
“
A
n
o
t
e
o
n
t
h
e
v
a
l
i
d
i
t
y
o
f
c
r
o
ss
-
v
a
l
i
d
a
t
i
o
n
f
o
r
e
v
a
l
u
a
t
i
n
g
a
u
t
o
r
e
g
r
e
ssi
v
e
t
i
me
se
r
i
e
s
p
r
e
d
i
c
t
i
o
n
,
”
C
o
m
p
u
t
a
t
i
o
n
a
l
S
t
a
t
i
st
i
c
s
a
n
d
D
a
t
a
An
a
l
y
si
s
,
v
o
l
.
1
2
0
,
p
p
.
7
0
–
8
3
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
s
d
a
.
2
0
1
7
.
1
1
.
0
0
3
.
[
2
5
]
L
.
S
a
n
t
o
so
a
n
d
P
r
i
y
a
d
i
,
“
C
o
mp
a
r
a
t
i
v
e
S
t
u
d
y
o
f
F
e
a
t
u
r
e
En
g
i
n
e
e
r
i
n
g
T
e
c
h
n
i
q
u
e
s
f
o
r
P
r
e
d
i
c
t
i
v
e
D
a
t
a
A
n
a
l
y
t
i
c
s,
”
J
o
u
r
n
a
l
o
f
T
e
c
h
n
o
l
o
g
y
I
n
f
o
rm
a
t
i
c
s
a
n
d
En
g
i
n
e
e
r
i
n
g
,
v
o
l
.
3
,
n
o
.
2
,
p
p
.
4
1
7
–
4
3
5
,
2
0
2
4
,
d
o
i
:
1
0
.
5
1
9
0
3
/
j
t
i
e
.
v
3
i
2
.
2
2
5
.
[
2
6
]
R
.
F
i
l
d
e
s,
S
.
M
a
,
a
n
d
S
.
K
o
l
a
ssa,
“
R
e
t
a
i
l
f
o
r
e
c
a
st
i
n
g
:
R
e
se
a
r
c
h
a
n
d
p
r
a
c
t
i
c
e
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
F
o
re
c
a
s
t
i
n
g
,
v
o
l
.
3
8
,
n
o
.
4
,
p
p
.
1
2
8
3
–
1
3
1
8
,
O
c
t
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
j
f
o
r
e
c
a
st
.
2
0
1
9
.
0
6
.
0
0
4
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
B
r
ia
n
Q
a
e
d
i
L
a
k
so
n
o
P
u
tr
a
re
c
e
i
v
e
d
th
e
B
a
c
h
e
lo
r’s
d
e
g
re
e
in
E
lec
tri
c
a
l
E
n
g
in
e
e
rin
g
f
ro
m
th
e
Un
iv
e
rsity
o
f
Bra
w
ij
a
y
a
,
M
a
lan
g
,
In
d
o
n
e
sia
,
a
n
d
c
u
rre
n
tl
y
u
n
d
e
rtak
in
g
th
e
M
a
ste
r’s
d
e
g
re
e
in
M
a
ste
r
o
f
T
e
c
h
n
o
lo
g
y
M
a
n
a
g
e
m
e
n
t
fro
m
th
e
In
stit
u
t
T
e
k
n
o
lo
g
i
S
e
p
u
l
u
h
No
p
e
m
b
e
r,
S
u
ra
b
a
y
a
,
In
d
o
n
e
sia
.
His
re
se
a
rc
h
in
tere
sts
in
c
l
u
d
e
m
a
c
h
in
e
lea
rn
in
g
,
f
o
re
c
a
stin
g
,
a
n
d
sp
a
re
p
a
rts
m
a
n
a
g
e
m
e
n
t.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
b
rian
.
q
a
e
d
i@g
m
a
il
.
c
o
m
.
J
e
r
r
y
D
w
i
Tr
ijo
y
o
Pu
r
n
o
m
o
re
c
e
iv
e
d
th
e
B
a
c
h
e
lo
r
a
n
d
M
a
ste
r
d
e
g
re
e
s
f
ro
m
De
p
a
rtme
n
t
o
f
S
tatist
ics
,
I
n
stit
u
t
T
e
k
n
o
lo
g
i
S
e
p
u
l
u
h
No
p
e
m
b
e
r,
In
d
o
n
e
sia
,
a
n
d
h
is
D
o
c
t
o
ra
l
d
e
g
re
e
f
ro
m
In
stit
u
te
o
f
S
tatisti
c
s,
Na
ti
o
n
a
l
Ch
iao
T
u
n
g
Un
iv
e
rsity
,
T
a
i
wa
n
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
b
i
o
sta
ti
stic,
b
i
o
i
n
f
o
rm
a
ti
c
s,
m
a
c
h
in
e
lea
rn
in
g
a
n
d
b
ig
d
a
ta
a
n
a
ly
ti
c
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
jerry
@its.
a
c
.
id
.
Evaluation Warning : The document was created with Spire.PDF for Python.